Adolfo Delorenzo a4ef775731 Implement comprehensive rate limiting to protect against DoS attacks

- Add token bucket rate limiter with sliding window algorithm
- Implement per-endpoint configurable rate limits
- Add automatic IP blocking for excessive requests
- Implement global request limits and concurrent request throttling
- Add request size validation for all endpoints
- Create admin endpoints for rate limit management
- Add rate limit headers to responses
- Implement cleanup thread for old rate limit buckets
- Create detailed rate limiting documentation

Rate limits:
- Transcription: 10/min, 100/hour, max 10MB
- Translation: 20/min, 300/hour, max 100KB
- Streaming: 10/min, 150/hour, max 100KB
- TTS: 15/min, 200/hour, max 50KB
- Global: 1000/min, 10000/hour, 50 concurrent

Security features:
- Automatic temporary IP blocking (1 hour) for abuse
- Manual IP blocking via admin endpoint
- Request size validation to prevent large payload attacks
- Burst control to limit sudden traffic spikes

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

2025-06-03 00:14:05 -06:00

3.1 KiB

Raw Blame History

Voice Language Translator

A mobile-friendly web application that translates spoken language between multiple languages using:

Gemma 3 open-source LLM via Ollama for translation
OpenAI Whisper for speech-to-text
OpenAI Edge TTS for text-to-speech

Supported Languages

Arabic
Armenian
Azerbaijani
English
French
Georgian
Kazakh
Mandarin
Farsi
Portuguese
Russian
Spanish
Turkish
Uzbek

Setup Instructions

Install the required Python packages:
```
pip install -r requirements.txt
```

Configure environment variables:

# Copy the example environment file
cp .env.example .env

# Edit with your actual values
nano .env

# Or set directly:
export TTS_API_KEY="your-tts-api-key"
export SECRET_KEY="your-secret-key"

⚠️ Security Note: Never commit API keys or secrets to version control. See SECURITY.md for details.

Make sure you have Ollama installed and the Gemma 3 model loaded:
```
ollama pull gemma3
```
Ensure your OpenAI Edge TTS server is running on port 5050.
Run the application:
```
python app.py
```
Open your browser and navigate to:
```
http://localhost:8000
```

Usage

Select your source language from the dropdown menu
Press the microphone button and speak
Press the button again to stop recording
Wait for the transcription to complete
Select your target language
Press the "Translate" button
Use the play buttons to hear the original or translated text

Technical Details

The app uses Flask for the web server
Audio is processed client-side using the MediaRecorder API
Whisper for speech recognition with language hints
Ollama provides access to the Gemma 3 model for translation
OpenAI Edge TTS delivers natural-sounding speech output

CORS Configuration

The application supports Cross-Origin Resource Sharing (CORS) for secure cross-origin usage. See CORS_CONFIG.md for detailed configuration instructions.

Quick setup:

# Development (allow all origins)
export CORS_ORIGINS="*"

# Production (restrict to specific domains)
export CORS_ORIGINS="https://yourdomain.com,https://app.yourdomain.com"
export ADMIN_CORS_ORIGINS="https://admin.yourdomain.com"

Connection Retry & Offline Support

Talk2Me handles network interruptions gracefully with automatic retry logic:

Automatic request queuing during connection loss
Exponential backoff retry with configurable parameters
Visual connection status indicators
Priority-based request processing

See CONNECTION_RETRY.md for detailed documentation.

Rate Limiting

Comprehensive rate limiting protects against DoS attacks and resource exhaustion:

Token bucket algorithm with sliding window
Per-endpoint configurable limits
Automatic IP blocking for abusive clients
Global request limits and concurrent request throttling
Request size validation

See RATE_LIMITING.md for detailed documentation.

Mobile Support

The interface is fully responsive and designed to work well on mobile devices.

3.1 KiB Raw Blame History